Deep Cross Spectral Stereo Matching Using Multi-Spectral Image Fusion

• Published in: IEEE robotics and automation letters Vol. 7; no. 2; pp. 5373 - 5380
• Main Authors: Liang, Xiaolong, Jung, Cheolkon
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Cameras; Color matching; Computer vision; Consistency; Cross spectral; disparity estimation; Estimation; Feature extraction; Image fusion; Image processing; Image reconstruction; Infrared imagery; Material properties; multi-spectral fusion; Near infrared radiation; Parallax; Reconstruction; Skin; Smoothness; Spectra; Spectral bands; stereo matching; Task analysis; Unsupervised learning

Cross spectral stereo matching aims to estimate disparity from color (RGB) and near-infrared (NIR) image pairs. The main difference from traditional stereo matching is that there is a big gap between two spectral bands, which makes cross spectral stereo matching a challenging task. In this letter, w...